Catálogo de publicaciones - libros

In this paper we apply a formal ontological framework in order to deconstruct two prominent approaches to navigation from cognitive robotics, the Spatial Semantic Hierarchy of Kuipers and the Route Graph of Krieg-Brückner, Werner and others. The ontological framework is based on our current work on ontology specification, where we are investigating Masolo ’s Descriptive Ontology for Linguistic and Cognitive Engineering (DOLCE) extended particularly for space and navigation by incorporating aspects of Smith ’s Basic Formal Ontology (BFO). Our conclusion is that ontology should necessarily play an important role in the design and modelling of cognitive robotic systems: comparability between approaches is improved, modelling gaps and weaknesses are highlighted, re-use of existing formalisations is facilitated, and extensions for interaction with other components, such as natural language systems, are directly supported.

This paper describes the general concept of RouteGraphs, to be used for navigation by various agents in a variety of scenarios. We introduce the concept of an ontology and describe the modelling of general graphs as an example. This approach is then applied to define a “light-weight” ontology of RouteGraphs in an indoors environment, giving at first just a taxonomy of (sub)classes and relations between them, as well as to other (spatial) ontology. Finally, we show how to formalise ontology using a First Order Logic approach, and give an outline of how to develop actual data structures and algorithms for RouteGraphs.

A route graph as proposed in Werner et al. (2000) is a spatial representation of the environment that focuses on integrating qualitatively different routes an agent can use for navigation. In this paper we describe how a route graph based on the generalized Voronoi diagram (GVD) of the environment can be used for mobile robot mapping and navigation tasks in an office-like indoor environment. We propose a hierarchical organization of the graph structure resulting in more abstract layers that represent the environment at coarser levels of granularity. For this purpose, we define relevance measures to weight the meet points in the GVD based on how significant they are for navigation and present an algorithm that utilizes these weights to generate the coarser route graph layers. Computation of the relevance values from either complete or incomplete information about the environment is considered. Besides robot navigation, the techniques developed can be employed for other tasks in which abstract route graph representations are advantageous, e.g. automatically generating route descriptions from floor plans.

We present an approach which uses 2D and 3D landmarks for solving the correspondence problem in Simultaneous Localisation and Mapping (SLAM) in cognitive robot mapping. The nodes in the topological map are a representation for each local space the robot visits. The 2D approach is feature based – a neural network algorithm is used to learn a landmark signature from a set of features extracted from each local space representation. Newly encountered local spaces are classified by the neural network as to how well they match the signatures of the nodes in the topological network. The 3D landmarks are computed from camera views of the local space. Using multiple 2D views, identified landmarks are projected, with their correct location and orientation into 3D world space by scene reconstruction. As the robot moves around the local space, extracted landmarks are integrated into the ASR’s scene representation which comprises the 3D landmarks. The landmarks for an ASR scene are compared against the landmark scenes for previously constructed ASRs to determine when the robot is revisiting a place it has been to before.

This paper presents a very efficient SLAM algorithm that works by hierarchically dividing the map into local regions and subregions. At each level of the hierarchy each region stores a matrix representing some of the landmarks contained in this region. For keeping the matrices small only those landmarks are represented being observable from outside the region. A measurement is integrated into a local subregion using () computation time for landmarks in a subregion. When the robot moves to a different subregion a global update is necessary requiring only ( log ) computation time for overall landmarks. The algorithm is evaluated for map quality, storage space and computation time using simulated and real experiments in an office environment.

Establishing a clean relationship between a robot’s spatial model and natural language components is a non-trivial task, but is key to designing verbally controlled, navigating service robots. In this paper we examine the issues involved in the development of dialogue controlled navigating robots. In particular, we treat our robots as so-called , where robot and user cooperate to achieve a shared goal. We begin by characterising four categories of Shared Control Problems that affect verbally controlled navigating robots. Producing solutions to these problems requires a clear methodology in the linking of ’common-sense’ representations of space used by the robots, and the language interface. To this end, we present the as a general purpose, agent-based dialogue control system that provides a suitable framework for relating spatial information to natural language communication. To illustrate our approach, we focus in particular on natural language understanding, and show how natural language utterances may be mapped to formally modelled spatial concepts, thus helping to overcome problems in shared control.

In the autonomous piloting of vehicles, the characterization of nearby dynamic object motion by perception and tracking techniques aids in the optimization of avoidance strategies. Knowledge of the features of object motion in goal-driven navigation allows for accurate deviation strategies to be implemented with appropriate anticipation. This perceptual competence is a fundamental issue in the design of unmanned commercial outdoor vehicles with an often reduced capability for maneuvering. To this aim, a grid map representation of the local panorama is proposed such that laser rangefinder images are converted into grid cells that are segmented and assigned to objects, allowing classification and monitoring. The motion properties of objects are thus used to establish avoidance behavior to smartly control the vehicle steering, such that a safe and optimal detour maneuver is carried out while driving to a target. The developed perceptual ability is demonstrated here in several tests performed in a relatively clutter-free area to detect and track walking pedestrians. Some results are also shown to highlight the modulation of moving object properties on trajectories described by a robot when a fuzzy avoidance strategy is used to control the steering angle.